## 1871 – AI Tech Challenge
## Context

The company receives millions of calls from its customers every month and the calls are serviced by thousands of agents. The call channel is one of the primary channels through which customers inquire, provide feedback about the product and services, and raise any concerns. So, the call channel and the subsequent interactions with customers are key to delivering an exceptional customer experience and gaining insights into the needs of the customers.

The customer interaction data obtained through these calls provides valuable data to the operations and other groups within the company. The voice data, when transcribed and mined appropriately, can act as a secondary data source, and can enable the firm to identify new opportunities. 

The following are some of the use cases of transcribed data with near-term business benefits:
- Assessment of the level of customer satisfaction with a call interaction and the reasons for satisfaction or dissatisfaction.
- Identification of complaints associated with products or services so that complaints can be addressed efficiently and expeditiously.
- Understanding the context of the call so that the feedback and opportunities can be summarized and shared with the product development teams.
- Understanding the topic(s) associated with the calls so that customer service agents can be trained to address questions associated with multiple topics with minimal call transfers.

## Goal of the Competition
With the proliferation of Transformer-based-models aiding Natural Language Processing and Understanding, the company is interested in exploring opportunities to enhance current voice to text transcription capability to aid several downstream analytical, reporting, and modeling tasks. Taking advantage of Large Language Model, *******the challenge is to build a reliable voice-to-text transcription model. *******

## Challenge Overview
The training data for this challenge consists of audio files and their respective transcribed text. The test data only includes the audio files, that you will need to transcribe and submit. While your submission for the leaderboard will be scored on the accuracy of your transcribed text, we encourage you to take this one step further and perform a topic modeling step on the transcribed text to identify the main topic of the audio, saved as a list of strings of "topics" in an additional column. This should not be included in your competition submission, but may be reviewed by the host and company.